CivArchive
Model Type
Base Model
Platform
Add Mirror
Better Human Motion H3/LTX 2.5 - v1.0-LTX2.5
NSFW
v1.0-LTX2.5
v1.0-MH3
v2.0-LTX2.3
v1.0-LTX2.3
Better human motion for H3/LTX 2.5
Natural and more consistent body movement
Trained on T2V but supports also I2V
720x1280 resolution with 15-30 steps
Weight 0.4-0.8 is recommended
⚠️
Avoid prompt bleeding using shorter sentences or words
Description
First initial release in LTX 2.5
FAQ
What is Better Human Motion H3/LTX 2.5?
How do I use Better Human Motion H3/LTX 2.5?
Why might this LoRA not be producing the expected results?
Can I use this LoRA commercially?
What files are available and where can I download them?
LORA
LTXV 2.5
by
AdaptiveVision
Download (Beta)
View on CivitAI
concept
i2v
t2v
lora
minimax
h3
ltx
Details
Downloads
236
Platform
CivitAI
Platform Status
Available
Created
11/3/2026
Updated
11/5/2026
Deleted
-
Files
mvmt_ltx_25_500.safetensors
Size:
408.32 MB
SHA256:
8e2799e1272c18bca341ee3da8f2496bde28e00dfedc624e1e6e691cf5667537
Mirrors
CivitAI (1 mirrors)
mvmt_ltx_25_500.safetensors